Real-Time Ellipse Detection for Robotics Applications

@article{Keipour2021RealTimeED,
  title={Real-Time Ellipse Detection for Robotics Applications},
  author={Azarakhsh Keipour and Guilherme A. S. Pereira and Sebastian A. Scherer},
  journal={IEEE Robotics and Automation Letters},
  year={2021},
  volume={6},
  pages={7009-7016}
}
We propose a new algorithm for real-time detection and tracking of elliptic patterns suitable for real-world robotics applications. The method fits ellipses to each contour in the image frame and rejects ellipses that do not yield a good fit. The resulting detection and tracking method is lightweight enough to be used on robots’ resource-limited onboard computers, can deal with lighting variations and detect the pattern even when the view is partial. The method is tested on an example… 

Figures and Tables from this paper

Detection and Physical Interaction with Deformable Linear Objects
TLDR
The recent work on detecting deformable linear objects is described, which uses the segmentation output of the existing methods to provide the initialization required by the tracking methods automatically and can work with crossings and can output the model desirable for physical interaction and simulation.
Mission-level Robustness with Rapidly-deployed, Autonomous Aerial Vehicles by Carnegie Mellon Team Tartan at MBZIRC 2020
TLDR
This approach utilizes common techniques in vision and control, and encodes robustness into mission structure through outcome monitoring and recovery strategies, and enables rapid deployment and requires no central communication.
Deformable One-Dimensional Object Detection for Routing and Manipulation
TLDR
An approach for detecting deformable one-dimensional objects which can handle crossings and occlusions which can be used for tasks such as routing and manipulation and automatically provides the initialization required by the tracking methods.
Carnegie Mellon Team Tartan: Mission-level Robustness with Rapidly Deployed Autonomous Aerial Vehicles in the MBZIRC 2020
TLDR
The approach is to leverage common techniques in vision and control and encode robustness into mission structure through outcome monitoring and recovery strategies, aided by a system infrastructure that allows for quick mission deployments under tight time constraints and no central communication.
Visual Servoing Approach for Autonomous UAV Landing on a Moving Vehicle
TLDR
A method to autonomously land an Unmanned Aerial Vehicle on a moving vehicle with a circular (or elliptical) pattern on the top using a visual servoing controller and the control laws generate velocity commands in all three dimensions, eliminating the need for a separate height controller.

References

SHOWING 1-10 OF 36 REFERENCES
Carnegie Mellon Team Tartan: Mission-level Robustness with Rapidly Deployed Autonomous Aerial Vehicles in the MBZIRC 2020
TLDR
The approach is to leverage common techniques in vision and control and encode robustness into mission structure through outcome monitoring and recovery strategies, aided by a system infrastructure that allows for quick mission deployments under tight time constraints and no central communication.
Visual Servoing Approach for Autonomous UAV Landing on a Moving Vehicle
TLDR
A method to autonomously land an Unmanned Aerial Vehicle on a moving vehicle with a circular (or elliptical) pattern on the top using a visual servoing controller and the control laws generate velocity commands in all three dimensions, eliminating the need for a separate height controller.
Fast high-precision ellipse detection method
A real-time and precise ellipse detector via edge screening and aggregation
TLDR
The proposed method runs much faster than the current speed leading methods with the comparable or higher F-measure, the computational costs of arc grouping and parameter estimation are dramatically reduced, and the fitting results are finely agreeable to the actual ellipse contours.
Ellipse R-CNN: Learning to Infer Elliptical Object From Clustering and Occlusion
TLDR
This work introduces the first CNN-based ellipse detector, called Ellipse R-CNN, to represent and infer occluded objects as ellipses, and demonstrates that this approach outperforms the state-of-the-art model and its three variants on both synthetic and real datasets of occluding and clustered elliptical objects.
Arc Adjacency Matrix-Based Fast Ellipse Detection
TLDR
Experiments show that the AAMED method outperforms the 12 state-of-the-art methods on 9 datasets as a whole, with reference to recall, precision, F-measure, and time-consumption.
A method for the Hough transform detection of circles and ellipses using a 1-dimensional array
  • A. Goneid, S. El-Gindi, A. Sewisy
  • Physics
    1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation
  • 1997
A method is proposed for the Hough transform detection of circles and ellipses in binary images using a 1D accumulator array. The method proceeds in two stages: the first stage detects N edge points
Fast vision‐based autonomous detection of moving cooperative target for unmanned aerial vehicle landing
TLDR
A fast and effective method, fast target detection (FTD), to detect the moving cooperative target for the unmanned aerial vehicle landing, and the target is composed of double circles and a cross, which has rapid speed and good performance.
Ellipse proposal and convolutional neural network discriminant for autonomous landing marker detection
TLDR
A new landing marker detection algorithm for autonomous landing systems in a real environment using an ellipse detection algorithm to detect theEllipse landmark or other elliptical objects and convolution neural networks were utilized to obtain the correct landmarks.
...
...